Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tures
    -0.08
    	canvas
    -0.08
     pursuit
    -0.07
    imum
    -0.07
    蕃
    -0.07
    ி
    -0.07
    蒂
    -0.07
    氓
    -0.07
    zc
    -0.07
    brains
    -0.07
    POSITIVE LOGITS
    					
↵
    0.07
    					↵
    0.07
    		
↵
↵
    0.07
    🎞
    0.07
    人性化
    0.07
    网络游戏
    0.07
     eSports
    0.07
     fırs
    0.07
     행사
    0.07
     artworks
    0.06
    Act Density 0.028%

    No Known Activations